1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
|
#include <ctype.h>
#include "syntax.h"
#include "../src/utils.h"
typedef struct {
Word word_germ;
String lit_germ;
} LexingBuffer;
typedef struct {
TokenVec* token_pool;
TokenPtrVec* top_tokens;
} PseudoAst;
static void consolidate_buffer(LexingBuffer* buf, PseudoAst ps_ast) {
if (buf->lit_germ.count > 0) {
push_to_Word(&buf->word_germ, (Chunk){
.qmode = UN_Q,
.kind = CHUNK_LIT,
.as.lit_str = inner(&buf->lit_germ)
});
buf->lit_germ = make_String(256);
}
if (buf->word_germ.count > 0) {
Token* tok_ptr = push_to_TokenVec(ps_ast.token_pool, (Token){
.kind = TOK_WORD,
.as.word = buf->word_germ
});
push_to_TokenPtrVec(ps_ast.top_tokens, tok_ptr);
}
}
static Chunk collect_un_q_literal(char* line, size_t* pos) {
String buf = make_String(256);
size_t i;
for (i = *pos; line[*pos] != '$' && line[*pos] != '\0' && line[*pos] == ' '; i++) {
push_to_String(&buf, line[*pos]);
}
*pos = i;
return (Chunk){
.qmode = UN_Q,
.kind = CHUNK_LIT,
.as.lit_str = inner(&buf),
};
}
static Chunk collect_single_q_section(char* line, size_t* pos) {
(*pos)++;
String buf = make_String(256);
size_t i;
for (i = *pos; line[*pos] != '\'' && line[*pos] != '\0'; i++) {
push_to_String(&buf, line[*pos]);
}
if (line[i] == '\0') exit(44);
*pos = ++i;
return (Chunk){
.qmode = SINGLE_Q,
.kind = CHUNK_LIT,
.as.lit_str = inner(&buf)
};
}
static Chunk collect_double_q_section(char* line, size_t* pos) {
// TODO: add the extra double-q expansions
(*pos)++;
String buf = make_String(256);
size_t i;
for (i = *pos; line[*pos] != '\'' && line[*pos] != '\0'; i++) {
push_to_String(&buf, line[*pos]);
}
if (line[i] == '\0') exit(44);
*pos = ++i;
return (Chunk){
.qmode = DOUBLE_Q,
.kind = CHUNK_LIT,
.as.lit_str = inner(&buf)
};
}
DECLARE_MAYBE(SpecialToken, MaybeSpecialToken)
static MaybeSpecialToken recognize_spec_token(char* line, size_t* pos) {
// TODO: add more error guards for peekaheads
char next_ch;
switch (line[*pos]) {
case '|':
(*pos)++;
return (MaybeSpecialToken){.some = true, .value = SPEC_PIPE};
case '>':
next_ch = line[(*pos)+1];
switch (next_ch) {
case '(':
return (MaybeSpecialToken){.some = false};
case '>':
*pos += 2;
return (MaybeSpecialToken){.some = true, .value = SPEC_REDIR_W_APPEND};
default:
(*pos)++;
return (MaybeSpecialToken){.some = true, .value = SPEC_REDIR_W_TRUNC};
}
case '<':
next_ch = line[(*pos)+1];
if (line[(*pos)+1] == '(') {
return (MaybeSpecialToken){.some = false};
} else {
(*pos)++;
return (MaybeSpecialToken){.some = true, .value = SPEC_REDIR_R};
}
default:
return (MaybeSpecialToken){.some = false};
}
}
static void lex_level(char* line, size_t* pos, char until, PseudoAst ps_ast) {
LexingBuffer buf = {.word_germ = make_Word(256), .lit_germ = make_String(256)};
while (line[*pos] != until) {
if (line[*pos] == ' ') {
consolidate_buffer(&buf, ps_ast);
while (line[*pos] == ' ') (*pos)++;
continue;
}
MaybeSpecialToken m_spec = recognize_spec_token(line, pos);
if (m_spec.some) {
Token* tok_ptr = push_to_TokenVec(ps_ast.token_pool, (Token){
.kind = TOK_SPEC,
.as.spec = m_spec.value
});
push_to_TokenPtrVec(ps_ast.top_tokens, tok_ptr);
continue;
}
if (line[*pos] == '\'') {
Chunk chunk = collect_single_q_section(line, pos);
push_to_Word(&buf.word_germ, chunk);
} else if (line[*pos] == '\"') {
Chunk chunk = collect_double_q_section(line, pos);
push_to_Word(&buf.word_germ, chunk);
} else if (line[*pos] == '<' && line[(*pos)+1] == '(') {
*pos += 2;
consolidate_buffer(&buf, ps_ast);
TokenPtrVec procsub_toks = make_TokenPtrVec(256);
lex_level(line, pos, ')', (PseudoAst){
.token_pool = ps_ast.token_pool,
.top_tokens = &procsub_toks
});
(*pos)++; // consume ')'
Token* tok_ptr = push_to_TokenVec(ps_ast.token_pool, (Token){
.kind = TOK_SUB_IN,
.as.procsub_toks = procsub_toks,
});
push_to_TokenPtrVec(ps_ast.top_tokens, tok_ptr);
} else if (line[*pos] == '>' && line[(*pos)+1] == '(') {
*pos += 2;
consolidate_buffer(&buf, ps_ast);
TokenPtrVec procsub_toks = make_TokenPtrVec(256);
lex_level(line, pos, ')', (PseudoAst){
.token_pool = ps_ast.token_pool,
.top_tokens = &procsub_toks
});
(*pos)++; // consume ')'
Token* tok_ptr = push_to_TokenVec(ps_ast.token_pool, (Token){
.kind = TOK_SUB_OUT,
.as.procsub_toks = procsub_toks,
});
push_to_TokenPtrVec(ps_ast.top_tokens, tok_ptr);
}
}
}
Ast lex(char* input) {
size_t line_pos = 0;
TokenVec token_pool = make_TokenVec(256);
TokenPtrVec top_tokens = make_TokenPtrVec(256);
lex_level(input, &line_pos, '\0', (PseudoAst){
.token_pool = &token_pool,
.top_tokens = &top_tokens
});
return (Ast){.token_pool = token_pool, .top_tokens = top_tokens};
}
|
